© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14771
    Prev
    Next
    INDEX
    Explanations

    speaking, talking, staring, withdrawing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    წ
    0.36
    కుంది
    0.34
     compromise
    0.34
     côn
    0.34
     سوز
    0.33
     GPU
    0.31
     mals
    0.31
     rebels
    0.31
     حزب
    0.31
    熔
    0.31
    POSITIVE LOGITS
     mutter
    0.63
     hablar
    0.58
     mut
    0.55
    喃
    0.55
     berbicara
    0.54
    Talking
    0.54
    talking
    0.52
    coherent
    0.52
     falar
    0.52
     muttered
    0.52
    Activations Density 0.140%

    No Known Activations